DOE for Assay Developers Book
I have spent many years learning to apply Design of Experiments (DOE) to assay development. Most of the texts available have been written for engineers or statisticians. I feel that this has hampered the application of DOE in assay development.
To help my fellow assay developers learn DOE, I’m writing a book on the topic, but using only assay development applications and examples. My goal is to make it easier to understand DOE, and hopefully help it gain more widespread use.
I’ll be publishing the book one chapter at a time, as I finish writing them. In the spirit of increased scientific discourse, I will be giving the book away for free as PDF downloads on this website. Once it is finished, I will also offer a bound and printed edition for those that are interested.
Download Chapter 1 now! (right-click and choose “Save link as…”)
Table of Content
1.1 – One Factor At a Time (OFAT) and Interactions
1.2 – Factorial Experiments – foundations of DOE
1.3 – Fractional Factorials
1.4 – Statistical Power and Aliasing in Fractional Factorials
1.5 – Other Screening Designs
1.6 – How to Pick a Design – blocking, resolution, and power
1.7 – Response variables – what to measure?
Chapter 2- Analyzing Screening Designs
Chapter 3 – Response Surface Methodology
Chapter 4 – Special Designs
Copyright
This book is being published under a Creative Commons license. You are free to distribute this work to anyone you think would be interested, free of charge. You may not use any portion of this book for any commercial purpose without prior permission. You may create derivatives of this work, as long as these derivatives adhere to the same license restrictions.
For complete license information, please visit:
http://creativecommons.org/licenses/by-nc-sa/3.0/
5 Comments for DOE for Assay Developers Book
DOE Book Chapter 1! - Potencyassay.com | June 30, 2010 at 8:28 am
Rich Snyder | October 14, 2010 at 8:09 am
I often find myself attempting to validate a given RUO immunoassay to the stringency of a full CLIA-type validation. These immunoassays often fail the dilutional linearity and spike-recovery features of our validation due to matrix interference. This is also one of the features of an immunoassay that we focus most on during development, and I would like to include a Dilutional Linearity response alongside signal-to-noise and control recovery in my assay development DOE setup (using Design Expert from Statease and I prefer response surface methodology). I enjoyed your post about parallelism, and I usually attempt to do something similar (but not as rigorous) when I assess a given immunoassay buffer’s performance with respect to dilutional linearity, but I end up determining which buffer makes a given sample perform in a similar manner to the standards upon dilution by normalizing both the concentration and signal axis of the standard curve, and also normalizing the dilution series of the unknown sample in the same way and visually comparing the curves. This approach doesn’t seem to fit well into DOE software. Have you encountered a better way to include tests for dilutional behavior produced by a given immunoassay buffer into a DOE setting? More broadly, what are good responses to use for DOE focused on finding something to reduce matrix interference for a given assay?
Regards,
Rich
Joyce | April 1, 2011 at 8:02 am
Dan,
I really like the 1st chapter in your book. When do you plan on doing a Chapter on Blocking?
Thank you,
Joyce
Joyce | April 1, 2011 at 8:18 am
Dan,
Which software do you recommend for doing DOEs? I have used JMP in the past, and trying MiniTab.
Thank you again for starting this blog. It is a huge help!
Author comment by Dan | April 1, 2011 at 9:06 am
Hi Joyce,
Thanks for reading! You might have noticed that I haven’t been very active on this blog for a while so if anyone would want to post a guest article I would be all for it.
I’m currently working on the second chapter of the book which will probably mention blocking. I will also get into things like latin squares at a later time.
In terms of software, I’ve used both JMP and Minitab, but my favorite is still Design Expert. I’ve found it to have the nicest interface for designing and analyzing experiments.
Sincerely,
Dan
[...] DOE for Assay Developers Book [...]